Record companies invest billions of dollars in new talent around the globe each year. Gaining insight into what actually makes a hit song would provide tremendous benefits for the music industry. In this research we tackle this question by focussing on the dance hit song classification problem. A database of dance hit songs from 1985 until 2013 is built, including basic musical features, as well as more advanced features that capture a temporal aspect. A number of different classifiers are used to build and test dance hit prediction models. The resulting best model has a good performance when predicting whether a song is a "top 10" dance hit versus a lower listed position.

This summer, furniture company Kartell will start selling a new plastic chair designed by Philippe Starck – with some help. The system used – not, perhaps, strictly an AI – was a generative design software platform from Autodesk. Supplied with initial design goals, along with parameters such as materials, manufacturing methods and cost constraints, the software explores all the possible permutations of a solution to generate design alternatives. It tests and learns from each iteration what works and what doesn't. "As the relationship between the two matured, the system became a much stronger collaborative partner, and began to anticipate Starck's preferences and the way he likes to work," says Mark Davis, senior director of design futures at Autodesk.

The FLAIRS poster track is designed to promote discussion of emerging ideas and work in order to encourage and help guide researchers — especially new researchers — who are able to present a full poster in the conference poster session and receive that critical work-shaping feedback that helps guide good work into great work. Abstracts of those posters appear here, which we hope to see fully developed into future FLAIRS papers..

The Winograd Schema (WS) challenge has been proposed as an alternative to the Turing Test as a test for machine intelligence. In this paper we ‘situate’ the WS challenge in the data-information-knowledge continuum, suggesting in the process what a good WS is. Subsequently, we will argue that the WS is but a special case of a more general phenomenon in language understanding, namely the phenomenon of the ‘missing text’. In particular, we will argue that what we usually call thinking in the process of language understanding almost always involves discovering some missing text - text is rarely explicitly stated but is implicitly assumed as shared background knowledge. As such, we suggest extending the WS challenge to include other linguistic phenomena that also involve discovering the ‘missing text’, such tests metonymy, quantifier scope, lexical disambiguation, and copredication, to name a few.

In a variety of online settings involving interaction with end-users it is critical for the systems to adapt to changes in user preference. User preferences on items tend to change over time due to a variety of factors such as change in context, the task being performed, or other short-term or long-term external factors. Recommender systems, in particular need to be able to capture these dynamics in user preferences in order to remain tuned to the most current interests of users. In this work we present a recommendation framework which takes into account the dynamics of user preferences. We propose an approach based on Hidden Markov Models (HMM) to identify change-points in the sequence of user interactions which reflect significant changes in preference according to the sequential behavior of all the users in the data. The proposed framework leverages the identified change points to generate recommendations using a sequence-aware non-negative matrix factorization model. We empirically demonstrate the effectiveness of the HMM-based change detection method as compared to standard baseline methods. Additionally, we evaluate the performance of the proposed recommendation method and show that it compares favorably to state-of-the-art sequence-aware recommendation models.

Watching movies is one of the most popular entertainments among people. Every year, a huge amount of money goes to the movie industry to release movies to the market. In this paper, we propose a multimodal model to predict the likability of movies using textual, visual and product features. With the help of these features, we capture different aspects of movies and feed them as inputs to binary and multi-class classification and regression models to predict IMDB rating of movies at early steps of production. We also propose our own dataset consisting of about 15000 movie subtitles along with their metadata and poster images. We achieve 76% and 63% weighted F-score for binary and multiclass classification respectively, and 0.7 mean square error for the regression model.

Many recommender systems suffer from popularity bias: popular items are recommended frequently while less popular, niche products, are recommended rarely or not at all. However, recommending the ignored products in the ``long tail'' is critical for businesses as they are less likely to be discovered. In this paper, we introduce a personalized diversification re-ranking approach to increase the representation of less popular items in recommendations while maintaining acceptable recommendation accuracy. Our approach is a post-processing step that can be applied to the output of any recommender system. We show that our approach is capable of managing popularity bias more effectively, compared with an existing method based on regularization. We also examine both new and existing metrics to measure the coverage of long-tail items in the recommendation.

Auditing algorithms has emerged as a methodology for holding algorithms accountable by testing whether they are fair. This process often relies on the repeated use of a platform to record inputs and their corresponding outputs. For example, to audit Google search, one repeatedly inputs queries and captures the received search pages. The goal is then to discover, in the collected data, patterns that will reveal the ``secrets'' of algorithmic decision making. This knowledge discovery process makes some algorithm auditing tasks great applications for data mining techniques. In this paper, we introduce one particular algorithm audit, that of Google's Top stories. We describe the process of data collection, exploration, and analysis for this application and share some of the gleaned insights. Concretely, our analysis suggests that Google might be trying to burst the famous ``filter bubble'' by choosing less known publishers for the 3rd position in the Top stories.

In this work we introduce the problem of incendiary news detection. We compare and contrast this problem with the problem of hate speech detection in social media. Most of the social media posts that are classified as hate speech contain straightforward slurs, insults, swearing, etc. In contrast to social media posts, incendiary news articles often do not contain any straightforward slurs and insults but, nevertheless, incite hate. To detect such news articles, we leverage are source where activists attempt to combat hate on-line by manually tagging the news articles inciting hate. We collect non-incendiary news by retrieving news articles from the websites of the news agencies which are recognized world-wide as serious media that are highly unlikely to contain foul language (BBC, CNN). We run a classification experiment using several classification approaches. We demonstrate that our system differentiates between incendiary and non-incendiary news with 97.0% accuracy. We ensure the validity of our approach by using two different non-incendiary news corpora.

Methods that calculate dense vector representations for text have proven to be very successful for knowledge representation. We study how to estimate dense representations for multi-modal data (e.g., text, continuous, categorical). We propose Feat2Vec as a novel model that supports supervised learning when explicit labels are available, and self-supervised learning when there are no labels. Feat2Vec calculates embeddings for data with multiple feature types, enforcing that all embeddings exist in a common space. We believe that we are the first to propose a method for learning self-supervised embeddings that leverage the structure of multiple feature types. Our experiments suggest that Feat2Vec outperforms previously published methods, and that it may be useful for avoiding the cold-start problem.